Learning Path & Roadmap
Master AI and Machine Learning through interactive visualizations, mathematical derivations, and research-level deep dives.
Foundations (Statistics & Math)
5 ConceptsProbability
Understanding randomness and Bayesian vs Frequentist views.
Distributions
Normal, Binomial, and Poisson distributions.
Linear Algebra
Vectors, Matrices, Eigenvalues, and SVD.
Hypothesis Testing
p-values, Z-tests, and T-tests.
Convex Optimization & KKT
Lagrange multipliers, KKT optimality conditions, Slater condition, and duality.
Classical Machine Learning & Graph Learning
6 ConceptsLinear Regression
Predicting continuous values using a linear relationship.
Decision Trees
Hierarchical split-based classification and regression.
SVM
Support Vector Machines for optimal boundary separation.
K-Means Clustering
Unsupervised grouping of data points.
Statistical Learning Theory
VC Dimension, Rademacher complexity, generalization error bounds, and PAC learning.
Graph Neural Networks (GNNs)
Message passing paradigms, Graph Convolutional Networks (GCN), GraphSAGE, and non-Euclidean graph representations.
Deep Learning Architectures
6 ConceptsNeural Networks
The building blocks of deep learning: Perceptrons and MLPs.
Backpropagation
How neural networks learn using the chain rule.
RNNs & LSTMs
Backpropagation Through Time (BPTT), vanishing gradients, forget gates, and long-range sequence memory.
CNNs
Convolutional Neural Networks for image recognition.
Transformers
The attention mechanism that powers modern AI.
Attention Variants & Norms
Grouped-Query Attention (GQA), Multi-Query (MQA), RoPE embeddings, and RMSNorm topology.
Modern AI, Generative & Frontier Reasoning
11 ConceptsLLMs
Large Language Models and the GPT architecture.
RAG
Retrieval Augmented Generation for grounding AI.
RLHF
Reinforcement Learning from Human Feedback.
Frontier Reasoning & GRPO
DeepSeek-R1 style Group Relative Policy Optimization, rule-based RL, and test-time compute.
Agentic AI
Reasoning loops, tools, and multi-agent systems.
Generative Models
GANs, VAEs, and Diffusion Probabilistic Models (DDPM/DDIM).
Flow Matching & DiT Video
Rectified Flow matching, optimal transport vector fields, and Patchified Diffusion Transformers (Sora/Flux).
State Space Models & Mamba
Continuous-time SSMs, selective scan parameters, discretization, and linear-time sequence modeling.
Multimodal AI & CLIP
Contrastive vision-text embeddings, InfoNCE loss, and joint cross-modal representation spaces.
Mixture of Experts (MoE)
Sparse routing mechanisms, gating networks, Top-K dispatch, and auxiliary load balancing.
Mechanistic Interpretability
Sparse Autoencoders (SAEs), monosemantic feature dictionaries, circuit analysis, and activation steering.
AI Systems Engineering & MLOps
4 ConceptsDistributed Training
Parallelism paradigms (DDP, TP, PP, FSDP) and scaling laws.
Model Serving
High-throughput LLM hosting, KV caching, vLLM, speculative decoding, and quantization.
Quantization & LoRA
Low-Rank Adaptation (ΔW = B·A), rank selection, FP8/INT4 uniform quantization, and scale-zero point math.
FlashAttention & GPU Architecture
GPU HBM vs SRAM bandwidth, online softmax tiling, IO-awareness, and Triton CUDA ops.